An intelligent fault diagnosis method for column hydraulic system based on fourier transform convolutional block model-based convolutional neural network
GAO Yang
ZHANG Yue
ZHANG Yiming
Abstract：To address the issue of rapid and accurate fault diagnosis in mining hydraulic pillar systems,this paper proposes a fault diagnosis method combining Fourier Transform with an attention-based Convolutional Neural Network(FFT-CBAM-CNN).This method first uses Fourier Transform to convert the multi-channel one-dimensional time-domain signals of the hydraulic system into frequency-domain signals,capturing the frequency characteristics of the signals more effectively.Then,Convo-lutional Neural Networks(CNN)combined with Convolutional Block Attention Modules(CBAM)are employed for feature extraction and classification.Experimental results show that the FFT-CBAM-CNN based diagnosis method achieves an average accuracy of 97.75%with a standard deviation of 0.012 2,demonstrating higher accuracy and stability compared to methods using only CNN and FFT-CNN.
Keywords：hydraulic column systemfault diagnosisattention mechanismconvolutional neural net-workfourier transform
Publication Date：2026-02-28
Online Publishing Date：2026-01-31(First online date of this platform, not the publication date of the document)
Pages：9( 113-121 )